Representation Learning on Graphs: Methods and Applications

Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. The primary challenge in this domain is finding a way to represent, or encode, graph structure so that it can be easily exploited by machine learning models. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural information about a graph (e.g., degree statistics or kernel functions). However, recent years have seen a surge in approaches that automatically learn to encode graph structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction. Here we provide a conceptual review of key advancements in this area of representation learning on graphs, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks. We review methods to embed individual nodes as well as approaches to embed entire (sub)graphs. In doing so, we develop a unified framework to describe these recent approaches, and we highlight a number of important applications and directions for future work.

• Publication year

  2017

• Venue

  IEEE Data Engineering Bulletin

• Publication date

  2017-09-17

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1709.05584
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Graph Embedding Techniques, Applications, and Performance: A Survey

  2017influential reference
• Neural Message Passing for Quantum Chemistry

  2017cited by this paper
• Learning Structural Node Embeddings via Diffusion Wavelets

  2017influential reference
• Inductive Representation Learning on Large Graphs

  2017cited by this paper
• Neural Embeddings of Graphs in Hyperbolic Space

  2017cited by this paper
• metapath2vec: Scalable Representation Learning for Heterogeneous Networks

  2017cited by this paper
• struc2vec: Learning Node Representations from Structural Identity

  2017cited by this paper
• Predicting multicellular function through multi-layer tissue networks

  2017cited by this paper
• HARP: Hierarchical Representation Learning for Networks

  2017cited by this paper
• Modeling Relational Data with Graph Convolutional Networks

  2017cited by this paper
• UvA-DARE ( Digital Academic Repository ) Graph Convolutional Matrix Completion

  2017cited by this paper
• Column Networks for Collective Classification

  2016cited by this paper
• Molecular graph convolutions: moving beyond fingerprints

  2016cited by this paper
• Learning Convolutional Neural Networks for Graphs

  2016cited by this paper
• Discriminative Embeddings of Latent Variable Models for Structured Data

  2016influential reference
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

  2016cited by this paper
• Semi-Supervised Classification with Graph Convolutional Networks

  2016influential reference
• Higher-order organization of complex networks

  2016cited by this paper
• Asymmetric Transitivity Preserving Graph Embedding

  2016influential reference
• Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change

  2016cited by this paper
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

  2016cited by this paper
• Revisiting Semi-Supervised Learning with Graph Embeddings

  2016influential reference
• Walklets: Multiscale Graph Embeddings for Interpretable Network Classification

  2016cited by this paper
• Motifs in Temporal Networks

  2016cited by this paper
• Variational Graph Auto-Encoders

  2016influential reference
• Deep Neural Networks for Learning Graph Representations

  2016cited by this paper
• Geometric Deep Learning: Going beyond Euclidean data

  2016cited by this paper
• Local Modeling of Attributed Graphs: Algorithms and Applications

  2016cited by this paper
• Structural Deep Network Embedding

  2016cited by this paper
• node2vec: Scalable Feature Learning for Networks

  2016influential reference
• Don't Walk, Skip!: Online Learning of Multi-scale Network Embeddings

  2016cited by this paper
• GraRep: Learning Graph Representations with Global Structural Information

  2015influential reference
• LINE: Large-scale Information Network Embedding

  2015influential reference
• Gated Graph Sequence Neural Networks

  2015influential reference
• A Review of Relational Machine Learning for Knowledge Graphs

  2015influential reference
• Convolutional Networks on Graphs for Learning Molecular Fingerprints

  2015influential reference
• Heterogeneous Network Embedding via Deep Architectures

  2015cited by this paper
• DeepWalk: online learning of social representations

  2014influential reference
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

  2014cited by this paper
• Spectral Networks and Locally Connected Networks on Graphs

  2013influential reference
• Distributed large-scale natural graph factorization

  2013influential reference
• RolX: structural role extraction & mining in large graphs

  2012cited by this paper
• Node Classification in Social Networks

  2011cited by this paper
• Supervised random walks: predicting and recommending links in social networks

  2010cited by this paper
• Community detection in graphs

  2009cited by this paper
• The Graph Neural Network Model

  2009influential reference
• Visualizing Data using t-SNE

  2008cited by this paper
• Graph Kernels

  2008cited by this paper
• Survey of graph database models

  2008cited by this paper
• Introduction to Statistical Relational Learning

  2007cited by this paper
• Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks

  2006cited by this paper
• A new model for learning in graph domains

  2005cited by this paper
• Link-Based Classification

  2003cited by this paper
• The link prediction problem for social networks

  2003cited by this paper
• From Visual Data Exploration to Visual Data Mining: A Survey

  2003cited by this paper
• Latent Space Approaches to Social Network Analysis

  2002cited by this paper
• Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering

  2001influential reference
• A global geometric framework for nonlinear dimensionality reduction.

  2000cited by this paper
• Loopy Belief Propagation for Approximate Inference: An Empirical Study

  1999cited by this paper
• Long Short-Term Memory

  1997cited by this paper
• A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise

  1996cited by this paper
• Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis

  1964cited by this paper

• Deep neural network-based coupling model of inter-organizational knowledge flow and agent collaborative decision-making

  2026cites this paper
• Both ends of artificial intelligence impacting privacy: a review of violation and protection.

  2026cites this paper
• Leveraging Discrete Semantic Prototypes for Representation Learning on Text-Attributed Graphs

  2026cites this paper
• Latent Structural Similarity Networks for Unsupervised Discovery in Multivariate Time Series

  2026cites this paper
• Learning to Recommend Multi-Agent Subgraphs from Calling Trees

  2026cites this paper
• GraphSeek: Next-Generation Graph Analytics with LLMs

  2026cites this paper
• Feature Fusion‐Based Hybrid Quantum‐Classical Graph Residual Neural Network

  2026cites this paper
• MVCL: a multi-view contrastive learning framework for biomedical knowledge graphs

  2026cites this paper
• Clinical Data Goes MEDS? Let's OWL make sense of it

  2026cites this paper
• Bayesian Optimization for Quantum Error-Correcting Code Discovery

  2026cites this paper
• Enhancing deep hashing with graph filters and autoencoder-based embeddings

  2026cites this paper
• BEACON: predicting side effects and therapeutics outcomes to drugs by Bridging knowlEdge grAph with CONtextual language model

  2026cites this paper
• FARGO: Feature-Augmented Representation Learning Combined With Enhanced GraphSAGE for Community Detection

  2026cites this paper
• A Machine Learning Model for Predicting Collaboration in Regional Co-Authorship Network

  2026cites this paper
• engGNN: A Dual-Graph Neural Network for Omics-Based Disease Classification and Feature Selection

  2026cites this paper
• Deep Generative Models for Node Embedding and Neighborhood Prediction in Dynamic Graphs of Recommendation Systems

  2026cites this paper
• TriTopic: Tri-Modal Graph-Based Topic Modeling with Iterative Refinement and Archetypes

  2026cites this paper
• Rapid surrogate modelling of water-hammer in water distribution networks using spatiotemporal graph convolutional networks

  2026cites this paper
• PIMPC-GNN: Physics-Informed Multi-Phase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networks

  2026cites this paper
• Predicting multi period flood cascades and community failure in EV charging networks

  2026cites this paper
• Defending Attacks on Anti-Fraud Model With Generative Graph Representations

  2026cites this paper
• Multi-Source Localization Based on Graph Representation Learning and Bayesian Optimization

  2026cites this paper
• A Review of State-of-the-Art Deep Learning Models for Knowledge Graphs

  2026cites this paper
• Formats of representation in large language models

  2026cites this paper
• Graph Variate Neural Networks

  2025cites this paper
• Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses

  2025cites this paper
• Structure-Exploiting Reinforcement Learning for Networked Systems

  2025cites this paper
• A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language Models

  2025cites this paper
• Exploring the structure of the school curriculum with graph neural networks

  2025cites this paper
• Exploring Heterophily in Graph-level Tasks

  2025cites this paper
• Anti-Money Laundering Systems Using Deep Learning

  2025cites this paper
• Towards fair graph-based machine learning software: unveiling and mitigating graph model bias

  2025cites this paper
• Disentangled Dynamic Intrusion Detection

  2025cites this paper
• GRAVITY: A Controversial Graph Representation Learning for Vertex Classification

  2025influential citation
• Respiratory Signal Estimation for Free-Hand 2D Ultrasound Image via Heterogeneous Alignment and Conditional Generative Learning

  2025cites this paper
• GBGC: Efficient and Adaptive Graph Coarsening via Granular-ball Computing

  2025cites this paper
• Learnable Diffusion Distances for Link Prediction

  2025cites this paper
• The connectivity dimension of a graph

  2025cites this paper
• GCL-ALG: graph contrastive learning with adaptive learnable view generators

  2025cites this paper
• Language Embedding Meets Dynamic Graph: A New Exploration for Neural Architecture Representation Learning

  2025cites this paper
• Nonparametric Teaching for Graph Property Learners

  2025cites this paper
• Rhomboid Tiling for Geometric Graph Deep Learning

  2025cites this paper
• NeuBM: Mitigating Model Bias in Graph Neural Networks through Neutral Input Calibration

  2025cites this paper
• A Novel Graph Neural Network Approach for Inverse Kinematics in Robotic Arms

  2025cites this paper
• Are Graph Attention Networks Able to Model Structural Information?

  2025cites this paper
• Lurie Networks with Robust Convergent Dynamics

  2025cites this paper
• Information bottleneck for link prediction

  2025cites this paper
• Higher-Order Graph Databases

  2025cites this paper
• Emotion Recognition from Audio Data Using Graph Neural Networks

  2025cites this paper
• Link Prediction in Social Networks Using the HTOA

  2025cites this paper
• Hyperbolic graph representation learning: methods, applications and challenges - A survey

  2025cites this paper
• Prédiction d'événements cliniques à partir des parcours de soins de patients représentés par des graphes de connaissances temporels

  2025cites this paper
• Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face

  2025cites this paper
• GLIDR: Graph-Like Inductive Logic Programming with Differentiable Reasoning

  2025cites this paper
• Leveraging Personalized PageRank and Higher-Order Topological Structures for Heterophily Mitigation in Graph Neural Networks

  2025cites this paper
• EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction

  2025cites this paper
• An Efficient Hybridization of Graph Representation Learning and Metaheuristics for the Constrained Incremental Graph Drawing Problem

  2025cites this paper
• Online Graph Partition for Distributed Dynamic GNN Training

  2025cites this paper
• A Hybrid Graph Neural Network Model for Predicting Cyber Attacks From Heterogeneous and Dynamic Network Data

  2025cites this paper
• Graph Neural Networks for Drug–Drug Interaction Prediction—Predicting Safe Drug Pairings with AI

  2025cites this paper
• Batch-agnostic dynamic GNN for mitigating temporal discontinuity

  2025cites this paper
• Enriching Pre-Training Using Fuzzy Logic

  2025cites this paper
• Group detection in energy commodity markets through manifold-informed Wasserstein barycenter

  2025cites this paper
• Landmark-Based Node Representations for Shortest Path Distance Approximations in Random Graphs

  2025cites this paper
• MSGCN: Multiplex Spatial Graph Convolution Network for Interlayer Link Weight Prediction

  2025cites this paper
• A Perspective on Foundation Models in Chemistry

  2025cites this paper
• FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs

  2025cites this paper
• Molecular Dynamics-Powered Hierarchical Geometric Deep Learning Framework for Protein-Ligand Interaction

  2025cites this paper
• Efficient Learning on Large Graphs using a Densifying Regularity Lemma

  2025cites this paper
• Dynamic graph contrastive learning based on learnable view generators

  2025cites this paper
• Graph-to-Text Generation with Bidirectional Dual Cross-Attention and Concatenation

  2025cites this paper
• Predicting primary delay of train services using graph-embedding based machine learning

  2025cites this paper
• How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings

  2025cites this paper
• Path Pooling: Train-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation

  2025cites this paper
• All Your Knowledge Belongs to Us: Stealing Knowledge Graphs via Reasoning APIs

  2025cites this paper
• AAHIN: attribute-aware heterogeneous information network representation learning for data mining

  2025cites this paper
• GraphSense: Graph Embedding Based Code Suggestion Framework

  2025cites this paper
• Heterogeneous Graph Structure Learning through the Lens of Data-generating Processes

  2025cites this paper
• Cross-Domain Inductive Applications with Unsupervised (Dynamic) Graph Neural Networks(GNN): Leveraging Siamese GNN and Energy-Based PMI Optimization

  2025cites this paper
• Unsupervised Inductive Node Representation Learning for Dynamic Graphs

  2025cites this paper
• Uncovering latent biological function associations through gene set embeddings

  2025cites this paper
• Oxidation states in solids from data-driven paradigms

  2025cites this paper
• Prediction of Usage Probabilities of Shopping-Mall Corridors Using Heterogeneous Graph Neural Networks

  2025cites this paper
• DCGG: A Dynamically Adaptive and Hardware-Software Coordinated Runtime System for GNN Acceleration on GPUs

  2025cites this paper
• Federated Spectral Graph Transformers Meet Neural Ordinary Differential Equations for Non-IID Graphs

  2025cites this paper
• Exploring similarity patterns in a large scientific corpus

  2025cites this paper
• Assessing the Robustness and Reducibility of Multiplex Networks with Embedding-Aided Interlayer Similarities

  2025cites this paper
• HAMLET: Healthcare-focused Adaptive Multilingual Learning Embedding-based Topic Modeling

  2025cites this paper
• Graph Density Mutation Study to Improve Cyber-Physical Systems Intrusion Detection with Heterogeneous GNN and Express Edges

  2025cites this paper
• Neural Graduated Assignment for Maximum Common Edge Subgraphs

  2025cites this paper
• Synthesizing event semantics for geographical entity representation

  2025cites this paper
• Learn Beneficial Noise as Graph Augmentation

  2025cites this paper
• Graph neural networks informed locally by thermodynamics

  2025cites this paper
• Learned Adaptive Mesh Generation

  2025cites this paper
• Self-Supervised Graph Contrastive Pretraining for Device-level Integrated Circuits

  2025cites this paper
• Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization

  2025cites this paper
• Enhancing Cultural Heritage Archive Analysis via Automated Entity Extraction and Graph-Based Representation Learning

  2025influential citation
• Classification of ULK1 inhibitors and SAR analysis by machine learning methods

  2025cites this paper
• Comprehensive Review of Graph Neural Networks: Challenges, Classification, Architectures, Applications, and Potential Utility in Bioinformatics

  2025cites this paper
• UniDyG: A Unified and Effective Representation Learning Approach for Large Dynamic Graphs

  2025cites this paper